Tanzanian AI app helps farmers detect crop diseases early

TANZANIA – A growing number of smallholder farmers in Tanzania now use artificial intelligence to identify crop diseases quickly and at low cost through a locally built mobile application that experts say can cut harvest losses and support rural incomes.

The KilimoAI app, developed by computer scientist Dr. Neema Mduma and her colleague Hudson Laizer, uses machine learning to study photos of affected leaves and point out the most likely disease within seconds.

Farmers can download the app for free from the Google Play Store, and it runs on basic Android phones already common in rural areas.

Mduma, a lecturer at the Nelson Mandela African Institution of Science and Technology, said she came up with the idea after seeing farmers lose crops again and again because they could not access fast and correct diagnosis.

“The main problem we are addressing is the lack of quick, reliable, and affordable advice regarding disease diagnosis,” she said. “We want farmers to understand what is affecting their crops early and to take the right action before it’s too late.”

Farmers use the app by taking a photo of a diseased leaf and uploading it for analysis. The system studies details such as color changes and spots, then gives a likely diagnosis and advice on what to do next. Mduma said the team designed the interface with simple icons and Swahili language support so farmers with limited digital skills can use it with ease.

“The farmer only needs to open the app, take a photo of the leaf, and upload it,” she said.

Tested in the field and built with experts

The developers worked closely with farmers and agricultural specialists during development. The app also works with the Tanzania Agricultural Research Institute to ensure that guidance matches approved farming practices.

“The app focuses on approved pesticides and proper usage instructions while also promoting integrated pest management and non-chemical options where possible,” Mduma said.

Pilot use in areas such as Arusha and the Southern Highlands has shown strong interest. By mid 2025, tens of thousands of users had signed up, including farmers and extension officers. The team now plans to reach about 400,000 farmers by 2030.

In Seela Sing’isi ward in northern Tanzania, 53 year old farmer Roland Daniel Sarikikya said the app has changed how he handles crop health.

“Previously, I just used pesticides randomly, but this app makes my work easier,” he said, after the app identified maize streak virus from a leaf photo.

Expanding disease coverage

Mduma and her team continue to improve the system and widen its disease library. They have already developed models for black sigatoka in bananas, Fusarium wilt in soil based crops, and late blight in potatoes, with plans to add them into the app.

As Tanzania’s agricultural tech space grows, tools like KilimoAI show how local digital solutions can fill long standing gaps in farm advisory services and help farmers make better decisions about crop health.

Sign up to receive our email newsletters with the latest news updates and insights from Africa and the World HERE.